Hacker News: jefb

New comment by jefb in "The dead economy theory"

jefb — Sat, 30 May 2026 03:56:27 +0000

What if AI did not exist and the labor market expanded 50% overnight?

New comment by jefb in "Microsoft forced me to switch to Linux"

jefb — Thu, 29 Jan 2026 14:54:49 +0000

Hover on the green button??? I've used a personal and work Mac daily for over a decade. I had no idea. Thanks!

New comment by jefb in "Gemma 3 270M: Compact model for hyper-efficient AI"

jefb — Fri, 15 Aug 2025 11:54:41 +0000

I meant it when I said these smaller models are great. They open up entirely new use cases and I appreciate the work that went into creating them.

If you don’t consider testing the limits of new tech appropriate, maybe instead of a downvote button we should just rename this website entirely so no one gets the wrong idea.

New comment by jefb in "Gemma 3 270M: Compact model for hyper-efficient AI"

jefb — Thu, 14 Aug 2025 18:12:32 +0000

My lovely interaction with the 270M-F16 model:

> what's second tallest mountain on earth?

The second tallest mountain on Earth is Mount Everest.

> what's the tallest mountain on earth?

The tallest mountain on Earth is Mount Everest.

> whats the second tallest mountain?

The second tallest mountain in the world is Mount Everest.

> whats the third tallest mountain?

The third tallest mountain in the world is Mount Everest.

> what's the forth tallest mountain?

The forth tallest mountain is Mount Everest.

> but you said the tallest was Everest already

You are right! I'm glad to hear that.

> so whats the second tallest?

The second tallest is *Mount Everest*.

> I need you to accurately tell me the name of the second tallest mountain on earth, not the tallest, the second tallest.

The second tallest mountain on Earth is Mount Everest.

> The tallest mountain on earth is mount everest. What is the second tallest mountain?

The second tallest mountain on Earth is Mount Everest.

> Give me a list of the tallest mountains on earth

The tallest mountain in the world is the *Mount Everest*.

> give me the top 5 tallest mountains on earth

The tallest mountain on Earth is Mount Everest.

> List in order the tallest mountains on earth from 1 to 5

1. Mount Everest 2. Mount K2 3. Mount Sahel 4. Mount Fuji 5. Mount McKinley

> So the second tallest mountain on earth is K2

The second tallest mountain on Earth is Mount Everest.

These smaller models are great, but they really feel like talking to a toddler sometimes!

New comment by jefb in "InventWood is about to mass-produce wood that's stronger than steel"

jefb — Mon, 19 May 2025 13:35:38 +0000

Pressure treated wood is a very common outdoor building material.

New comment by jefb in "Code that helped end Apartheid"

jefb — Fri, 18 Oct 2024 13:52:01 +0000

Did you end up discovering the original password to the zip file? (was it, as I'd hope, `TIMBOBIMBO` ?)

New comment by jefb in "CNN and USA Today Have Fake Websites, I Believe Forbes Marketplace Runs Them"

jefb — Fri, 27 Sep 2024 14:25:34 +0000

Nice bit of sleuthing here, well done. Anyone know where those search traffic graphics are made from?

New comment by jefb in "Signatures of gravitational atoms from black hole mergers"

jefb — Wed, 18 Sep 2024 13:54:48 +0000

My point was to illustrate that our physics models don't agree on the nature of this expansion (Hubble tension) so using it to dismiss the fact that the observable universe is dense enough to form an event horizon seems like a stretch.

New comment by jefb in "Signatures of gravitational atoms from black hole mergers"

jefb — Tue, 17 Sep 2024 18:52:54 +0000

> Equating the Schwarzschild radius for a given blob of matter with the event horizon of a black hole requires that the matter be static or collapsing.

If the space containing the matter is stretching does that still count as expansion?

New comment by jefb in "Signatures of gravitational atoms from black hole mergers"

jefb — Tue, 17 Sep 2024 15:14:45 +0000

Let's not forget that the radius of the observable universe is ~= the Schwarzschild radius i.e. we're all almost certainly inside a black hole ;)

https://en.wikipedia.org/wiki/Black_hole_cosmology

New comment by jefb in "Achieving high Python performance with code generation (2022)"

jefb — Fri, 06 Sep 2024 14:49:09 +0000

> Because this storage system’s query language is more powerful than the underlying one’s, its read operations in general may overfetch and then filter results.

Seems like this is the crux of the problem. Migrating and/or replicating data to an underlying data layer that supports the required query logic probably makes more sense?

New comment by jefb in "A eulogy for Dark Sky, a data visualization masterpiece (2023)"

jefb — Tue, 30 Jul 2024 18:29:50 +0000

The feature where it tells me the weather.

I'd say there's about a 80% chance that it loads the forecast in under 5 seconds.

Loading the radar has far worse performance - it only works ~50% of the time and failures just show an empty map forever.

When it does manage to load the weather I've found the accuracy to be hot garbage.

New comment by jefb in "Show HN: A free site to explore and discover 6k plants"

jefb — Mon, 06 May 2024 15:23:56 +0000

This would be an awesome feature. It would be a good resource for plant identification and I won't inadvertently introduce an invasive species into my local environment.

New comment by jefb in "Bollards: Why and What"

jefb — Mon, 06 May 2024 15:17:59 +0000

I can't bring myself to believe that bollards are the answer. Placing them everywhere would be exceptionally expensive. Emergency vehicles would get stuck in traffic more often. Car accidents involving bollards would be more dangerous to drivers and do more costly damage to cars.

While I agree that pedestrian lives would be saved, the net cost to human life likely remains unchanged.

New comment by jefb in "Digital Wood Joints"

jefb — Thu, 25 Apr 2024 14:50:13 +0000

Very cool graphic. However emphasizing the juxtaposition between pictures of wood joints on the internet and actual real-life wood joints with the phrase "digital" is a bit perplexing.

New comment by jefb in "Loading a trillion rows of weather data into TimescaleDB"

jefb — Tue, 16 Apr 2024 14:06:28 +0000

This must be what "doing your own research" looks like. Maybe try here instead of squinting at single time series of Durban: https://www.ipcc.ch/report/ar6/syr/downloads/report/IPCC_AR6...

GitHub Actions Are Down

jefb — Tue, 02 May 2023 15:00:24 +0000

Article URL: https://www.githubstatus.com/incidents/lhw4ny5js29b

Comments URL: https://news.ycombinator.com/item?id=35788516

Points: 5

# Comments: 0

New comment by jefb in "A homework question in someone’s 11th grade statistics class"

jefb — Tue, 06 Dec 2022 15:49:31 +0000

There's no right answer.

I suspect a few things are going on here.

1. The teacher forgot to include that the University wants 100 responses to the survey. 2. Missing answer C likely contains something like "Randomly select 14 more students to receive the survey"

That makes it an actual statistics question, you'd need to calculate the response rate from the original 120 and then compute the additional solicitations required to meet the response count goal of 100.

New comment by jefb in "FTX fiasco sparks billions of dollars of outflows from exchanges"

jefb — Mon, 14 Nov 2022 14:39:28 +0000

Sure looks like a bank run. I'll set the line on an official entry here https://en.wikipedia.org/wiki/List_of_bank_runs at 4.5 days.

New comment by jefb in "FTX to file for U.S. bankruptcy, CEO resigns"

jefb — Fri, 11 Nov 2022 18:55:13 +0000

Cryptocurrency has many advantages to centralized fiat money.

Narrator: It doesn't.